Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

37 Lataukset (Pure)

Abstrakti

Domain adaptation is a common problem in robotics, with applications such as transferring policies from simulation to real world and lifelong learning. Performing such adaptation, however, requires informative data about the environment to be available during the adaptation. In this paper, we present domain curiosity—a method of training exploratory policies that are explicitly optimized to provide data that allows a model to learn about the unknown aspects of the environment. In contrast to most curiosity methods, our approach explicitly rewards learning, which makes it robust to environment noise without sacrificing its ability to learn. We evaluate the proposed method by comparing how much a model can learn about environment dynamics given data collected by the proposed approach, compared to standard curious and random policies. The evaluation is performed using a toy environment, two simulated robot setups, and on a real-world haptic exploration task. The results show that the proposed method allows data-efficient and accurate estimation of dynamics.
AlkuperäiskieliEnglanti
OtsikkoProceedings of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021
KustantajaIEEE
Sivut1259-1266
Sivumäärä8
ISBN (elektroninen)978-1-6654-1714-3
DOI - pysyväislinkit
TilaJulkaistu - 16 jouluk. 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaIEEE/RSJ International Conference on Intelligent Robots and Systems - Prague, Tshekki
Kesto: 27 syysk. 20211 lokak. 2021

Julkaisusarja

NimiProceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems
KustantajaIEEE
ISSN (painettu)2153-0858
ISSN (elektroninen)2153-0858

Conference

ConferenceIEEE/RSJ International Conference on Intelligent Robots and Systems
LyhennettäIROS
Maa/AlueTshekki
KaupunkiPrague
Ajanjakso27/09/202101/10/2021

Sormenjälki

Sukella tutkimusaiheisiin 'Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä